qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v3 16/60] target/riscv: vector integer min/max instructions
@ 2020-03-09 12:05 LIU Zhiwei
  2020-03-09 12:05 ` [PATCH v3 44/60] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
                   ` (6 more replies)
  0 siblings, 7 replies; 9+ messages in thread
From: LIU Zhiwei @ 2020-03-09 12:05 UTC (permalink / raw)
  To: richard.henderson, alistair23, chihmin.chao, palmer
  Cc: guoren, qemu-riscv, qemu-devel, wxy194768, wenmeng_zhang,
	LIU Zhiwei

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   | 33 ++++++++++++
 target/riscv/insn32.decode              |  8 +++
 target/riscv/insn_trans/trans_rvv.inc.c | 10 ++++
 target/riscv/vector_helper.c            | 71 +++++++++++++++++++++++++
 4 files changed, 122 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 4e6c47c2d2..c7d4ff185a 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -492,3 +492,36 @@ DEF_HELPER_6(vmsgt_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vmsgt_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vminu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmin_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmax_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vminu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmin_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmaxu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vmax_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 525b2fa442..a7619f4e3d 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -354,6 +354,14 @@ vmsgtu_vx       011110 . ..... ..... 100 ..... 1010111 @r_vm
 vmsgtu_vi       011110 . ..... ..... 011 ..... 1010111 @r_vm
 vmsgt_vx        011111 . ..... ..... 100 ..... 1010111 @r_vm
 vmsgt_vi        011111 . ..... ..... 011 ..... 1010111 @r_vm
+vminu_vv        000100 . ..... ..... 000 ..... 1010111 @r_vm
+vminu_vx        000100 . ..... ..... 100 ..... 1010111 @r_vm
+vmin_vv         000101 . ..... ..... 000 ..... 1010111 @r_vm
+vmin_vx         000101 . ..... ..... 100 ..... 1010111 @r_vm
+vmaxu_vv        000110 . ..... ..... 000 ..... 1010111 @r_vm
+vmaxu_vx        000110 . ..... ..... 100 ..... 1010111 @r_vm
+vmax_vv         000111 . ..... ..... 000 ..... 1010111 @r_vm
+vmax_vx         000111 . ..... ..... 100 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 078d275af6..4437a77878 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1424,3 +1424,13 @@ GEN_OPIVI_TRANS(vmsleu_vi, 1, vmsleu_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsle_vi, 0, vmsle_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsgtu_vi, 1, vmsgtu_vx, opivx_cmp_check)
 GEN_OPIVI_TRANS(vmsgt_vi, 0, vmsgt_vx, opivx_cmp_check)
+
+/* Vector Integer Min/Max Instructions */
+GEN_OPIVV_GVEC_TRANS(vminu_vv, umin)
+GEN_OPIVV_GVEC_TRANS(vmin_vv,  smin)
+GEN_OPIVV_GVEC_TRANS(vmaxu_vv, umax)
+GEN_OPIVV_GVEC_TRANS(vmax_vv,  smax)
+GEN_OPIVX_TRANS(vminu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmin_vx,  opivx_check)
+GEN_OPIVX_TRANS(vmaxu_vx, opivx_check)
+GEN_OPIVX_TRANS(vmax_vx,  opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index e7a4e99f46..03e001262f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -849,6 +849,10 @@ GEN_VEXT_AMO(vamomaxuw_v_w, uint32_t, uint32_t, idx_w, clearl)
 #define OP_SSS_H int16_t, int16_t, int16_t, int16_t, int16_t
 #define OP_SSS_W int32_t, int32_t, int32_t, int32_t, int32_t
 #define OP_SSS_D int64_t, int64_t, int64_t, int64_t, int64_t
+#define OP_UUU_B uint8_t, uint8_t, uint8_t, uint8_t, uint8_t
+#define OP_UUU_H uint16_t, uint16_t, uint16_t, uint16_t, uint16_t
+#define OP_UUU_W uint32_t, uint32_t, uint32_t, uint32_t, uint32_t
+#define OP_UUU_D uint64_t, uint64_t, uint64_t, uint64_t, uint64_t
 
 /* operation of two vector elements */
 #define OPIVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)    \
@@ -1479,3 +1483,70 @@ GEN_VEXT_CMP_VX(vmsgt_vx_b, int8_t,  H1, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_h, int16_t, H2, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_w, int32_t, H4, DO_MSGT)
 GEN_VEXT_CMP_VX(vmsgt_vx_d, int64_t, H8, DO_MSGT)
+
+/* Vector Integer Min/Max Instructions */
+RVVCALL(OPIVV2, vminu_vv_b, OP_UUU_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_h, OP_UUU_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_w, OP_UUU_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vminu_vv_d, OP_UUU_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_b, OP_SSS_B, H1, H1, H1, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_h, OP_SSS_H, H2, H2, H2, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_w, OP_SSS_W, H4, H4, H4, DO_MIN)
+RVVCALL(OPIVV2, vmin_vv_d, OP_SSS_D, H8, H8, H8, DO_MIN)
+RVVCALL(OPIVV2, vmaxu_vv_b, OP_UUU_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_h, OP_UUU_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_w, OP_UUU_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmaxu_vv_d, OP_UUU_D, H8, H8, H8, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_b, OP_SSS_B, H1, H1, H1, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_h, OP_SSS_H, H2, H2, H2, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_w, OP_SSS_W, H4, H4, H4, DO_MAX)
+RVVCALL(OPIVV2, vmax_vv_d, OP_SSS_D, H8, H8, H8, DO_MAX)
+GEN_VEXT_VV(vminu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vminu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vminu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vminu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmin_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmin_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmin_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmin_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmaxu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmaxu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmaxu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmaxu_vv_d, 8, 8, clearq)
+GEN_VEXT_VV(vmax_vv_b, 1, 1, clearb)
+GEN_VEXT_VV(vmax_vv_h, 2, 2, clearh)
+GEN_VEXT_VV(vmax_vv_w, 4, 4, clearl)
+GEN_VEXT_VV(vmax_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2, vminu_vx_b, OP_UUU_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_h, OP_UUU_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_w, OP_UUU_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vminu_vx_d, OP_UUU_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_b, OP_SSS_B, H1, H1, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_h, OP_SSS_H, H2, H2, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_w, OP_SSS_W, H4, H4, DO_MIN)
+RVVCALL(OPIVX2, vmin_vx_d, OP_SSS_D, H8, H8, DO_MIN)
+RVVCALL(OPIVX2, vmaxu_vx_b, OP_UUU_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_h, OP_UUU_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_w, OP_UUU_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmaxu_vx_d, OP_UUU_D, H8, H8, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_b, OP_SSS_B, H1, H1, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_h, OP_SSS_H, H2, H2, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_w, OP_SSS_W, H4, H4, DO_MAX)
+RVVCALL(OPIVX2, vmax_vx_d, OP_SSS_D, H8, H8, DO_MAX)
+GEN_VEXT_VX(vminu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vminu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vminu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vminu_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmin_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmin_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmin_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmin_vx_d, 8, 8, clearq)
+GEN_VEXT_VX(vmaxu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmaxu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmaxu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmaxu_vx_d, 8, 8,  clearq)
+GEN_VEXT_VX(vmax_vx_b, 1, 1, clearb)
+GEN_VEXT_VX(vmax_vx_h, 2, 2, clearh)
+GEN_VEXT_VX(vmax_vx_w, 4, 4, clearl)
+GEN_VEXT_VX(vmax_vx_d, 8, 8, clearq)
-- 
2.23.0



^ permalink raw reply related	[flat|nested] 9+ messages in thread
* [PATCH v3 00/60] target/riscv: support vector extension v0.7.1
@ 2020-03-09  8:19 LIU Zhiwei
  2020-03-09  8:20 ` [PATCH v3 48/60] target/riscv: vector mask-register logical instructions LIU Zhiwei
  0 siblings, 1 reply; 9+ messages in thread
From: LIU Zhiwei @ 2020-03-09  8:19 UTC (permalink / raw)
  To: richard.henderson, alistair23, chihmin.chao, palmer
  Cc: guoren, qemu-riscv, qemu-devel, wxy194768, wenmeng_zhang,
	LIU Zhiwei

This patchset implements the vector extension for RISC-V on QEMU.

You can also find the patchset and all *test cases* in
my repo(https://github.com/romanheros/qemu.git branch:vector-upstream-v3).
All the test cases are in the directory qemu/tests/riscv/vector/. They are
riscv64 linux user mode programs.

You can test the patchset by the script qemu/tests/riscv/vector/runcase.sh.

Features:
  * support specification riscv-v-spec-0.7.1.(https://github.com/riscv/riscv-v-spec/releases/tag/0.7.1/)
  * support basic vector extension.
  * support Zvlsseg.
  * support Zvamo.
  * not support Zvediv as it is changing.
  * SLEN always equals VLEN.
  * element width support 8bit, 16bit, 32bit, 64bit.

Changelog:
v3
  * move check code from execution-time to translation-time
  * use a continous memory block for vector register description.
  * vector registers as direct fields in RISCVCPUState.
  * support VLEN configure from qemu command line.
  * support ELEN configure from qemu command line.
  * support vector specification version configure from qemu command line.
  * probe pages before real load or store access.
  * use probe_page_check for no-fault operations in linux user mode.
  * generation atomic exit exception when in parallel environment.
  * fixup a lot of concrete bugs.

V2
  * use float16_compare{_quiet}
  * only use GETPC() in outer most helper
  * add ctx.ext_v Property


LIU Zhiwei (60):
  target/riscv: add vector extension field in CPURISCVState
  target/riscv: implementation-defined constant parameters
  target/riscv: support vector extension csr
  target/riscv: add vector configure instruction
  target/riscv: add vector stride load and store instructions
  target/riscv: add vector index load and store instructions
  target/riscv: add fault-only-first unit stride load
  target/riscv: add vector amo operations
  target/riscv: vector single-width integer add and subtract
  target/riscv: vector widening integer add and subtract
  target/riscv: vector integer add-with-carry / subtract-with-borrow
    instructions
  target/riscv: vector bitwise logical instructions
  target/riscv: vector single-width bit shift instructions
  target/riscv: vector narrowing integer right shift instructions
  target/riscv: vector integer comparison instructions
  target/riscv: vector integer min/max instructions
  target/riscv: vector single-width integer multiply instructions
  target/riscv: vector integer divide instructions
  target/riscv: vector widening integer multiply instructions
  target/riscv: vector single-width integer multiply-add instructions
  target/riscv: vector widening integer multiply-add instructions
  target/riscv: vector integer merge and move instructions
  target/riscv: vector single-width saturating add and subtract
  target/riscv: vector single-width averaging add and subtract
  target/riscv: vector single-width fractional multiply with rounding
    and saturation
  target/riscv: vector widening saturating scaled multiply-add
  target/riscv: vector single-width scaling shift instructions
  target/riscv: vector narrowing fixed-point clip instructions
  target/riscv: vector single-width floating-point add/subtract
    instructions
  target/riscv: vector widening floating-point add/subtract instructions
  target/riscv: vector single-width floating-point multiply/divide
    instructions
  target/riscv: vector widening floating-point multiply
  target/riscv: vector single-width floating-point fused multiply-add
    instructions
  target/riscv: vector widening floating-point fused multiply-add
    instructions
  target/riscv: vector floating-point square-root instruction
  target/riscv: vector floating-point min/max instructions
  target/riscv: vector floating-point sign-injection instructions
  target/riscv: vector floating-point compare instructions
  target/riscv: vector floating-point classify instructions
  target/riscv: vector floating-point merge instructions
  target/riscv: vector floating-point/integer type-convert instructions
  target/riscv: widening floating-point/integer type-convert
    instructions
  target/riscv: narrowing floating-point/integer type-convert
    instructions
  target/riscv: vector single-width integer reduction instructions
  target/riscv: vector wideing integer reduction instructions
  target/riscv: vector single-width floating-point reduction
    instructions
  target/riscv: vector widening floating-point reduction instructions
  target/riscv: vector mask-register logical instructions
  target/riscv: vector mask population count vmpopc
  target/riscv: vmfirst find-first-set mask bit
  target/riscv: set-X-first mask bit
  target/riscv: vector iota instruction
  target/riscv: vector element index instruction
  target/riscv: integer extract instruction
  target/riscv: integer scalar move instruction
  target/riscv: floating-point scalar move instructions
  target/riscv: vector slide instructions
  target/riscv: vector register gather instruction
  target/riscv: vector compress instruction
  target/riscv: configure and turn on vector extension from command line

 target/riscv/Makefile.objs              |    2 +-
 target/riscv/cpu.c                      |   49 +
 target/riscv/cpu.h                      |   89 +-
 target/riscv/cpu_bits.h                 |   15 +
 target/riscv/csr.c                      |   75 +-
 target/riscv/helper.h                   | 1075 +++++
 target/riscv/insn32-64.decode           |   11 +
 target/riscv/insn32.decode              |  366 ++
 target/riscv/insn_trans/trans_rvv.inc.c | 2386 ++++++++++++
 target/riscv/translate.c                |   24 +-
 target/riscv/vector_helper.c            | 4745 +++++++++++++++++++++++
 11 files changed, 8824 insertions(+), 13 deletions(-)
 create mode 100644 target/riscv/insn_trans/trans_rvv.inc.c
 create mode 100644 target/riscv/vector_helper.c

-- 
2.23.0



^ permalink raw reply	[flat|nested] 9+ messages in thread
end of thread, other threads:[~2020-03-09 12:12 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2020-03-09 12:05 [PATCH v3 16/60] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 44/60] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 45/60] target/riscv: vector wideing " LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 46/60] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 47/60] target/riscv: vector widening " LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 48/60] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 49/60] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-03-09 12:05 ` [PATCH v3 50/60] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
  -- strict thread matches above, loose matches on Subject: below --
2020-03-09  8:19 [PATCH v3 00/60] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-09  8:20 ` [PATCH v3 48/60] target/riscv: vector mask-register logical instructions LIU Zhiwei

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).